EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Off‐policy correction algorithm for double Q network based on deep reinforcement learning

Qingbo Zhang, Manlu Liu, Heng Wang, Weimin Qian, Xinglang Zhang

IET Cyber-Systems and Robotics · 2023-12 · 5 (4)

DOI: 10.1049/csy2.12102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Cyber-Systems and Robotics, online erschienen am 21.12.2023. Verfasst von Qingbo Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A deep reinforcement learning (DRL) method based on the deep deterministic policy gradient (DDPG) algorithm is proposed to address the problems of a mismatch between the needed training samples and the actual training samples during the training of intelligence, the overestimation and underestimation of the existence of Q‐values, and the insufficient dynamism of the intelligence policy exploration. This method introduces the Actor‐Critic Off‐Policy Correction (AC‐Off‐POC) reinforcement learning framework and an improved double Q‐value learning method, which enables the value function network in the target task to provide a more accurate evaluation of the policy network and converge to the optimal policy more quickly and stably to obtain higher value returns. The method is applied to multiple MuJoCo tasks on the Open AI Gym simulation platform. The experimental results show that it is better than the DDPG algorithm based solely on the different policy correction framework (AC‐Off‐POC) and the conventional DRL algorithm. The value of returns and stability of the double‐Q‐network off‐policy correction algorithm for the deep deterministic policy gradient (DCAOP‐DDPG) proposed by the authors are significantly higher than those of other DRL algorithms.

Zitieren

APA

Zhang, Q., Liu, M., Wang, H., Qian, W., & Zhang, X. (2023). Off‐policy correction algorithm for double Q network based on deep reinforcement learning. IET Cyber-Systems and Robotics, 5(4). https://doi.org/10.1049/csy2.12102

Vancouver

Zhang Q, Liu M, Wang H, Qian W, Zhang X. Off‐policy correction algorithm for double Q network based on deep reinforcement learning. IET Cyber-Systems and Robotics. 2023;5(4). doi:10.1049/csy2.12102

BibTeX
@article{Zhang2023,
  author = {Zhang, Qingbo and Liu, Manlu and Wang, Heng and Qian, Weimin and Zhang, Xinglang},
  title = {Off‐policy correction algorithm for double Q network based on deep reinforcement learning},
  journal = {IET Cyber-Systems and Robotics},
  year = {2023},
  volume = {5},
  number = {4},
  doi = {10.1049/csy2.12102}
}
Kostenlos starten →